Cover Image

Saliency-driven Dynamic Token Pruning for Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tao, Yao, Tang, Yehui, Wang, Yun, Zhu, Mingjian, Hu, Hailin, Wang, Yunhe
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
by: Bi, Zhenni, et al.
Published: (2024)

CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models
by: Tang, Zicong, et al.
Published: (2025)

DLP: Dynamic Layerwise Pruning in Large Language Models
by: Chen, Yuli, et al.
Published: (2025)

Pruning Large Language Models with Semi-Structural Adaptive Sparse Training
by: Huang, Weiyu, et al.
Published: (2024)

DPPA: Pruning Method for Large Language Model to Model Merging
by: Zhu, Yaochen, et al.
Published: (2024)

PanGu-$π$ Pro:Rethinking Optimization and Architecture for Tiny Language Models
by: Tang, Yehui, et al.
Published: (2024)

Hey, That's My Data! Token-Only Dataset Inference in Large Language Models
by: Xiong, Chen, et al.
Published: (2025)

DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration
by: Zhang, Hanzhi, et al.
Published: (2025)

Index-Preserving Lightweight Token Pruning for Efficient Document Understanding in Vision-Language Models
by: Son, Jaemin, et al.
Published: (2025)

Pruning as a Cooperative Game: Surrogate-Assisted Layer Contribution Estimation for Large Language Models
by: Ding, Xuan, et al.
Published: (2026)

Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning
by: Zhou, Hang, et al.
Published: (2024)

Full-ECE: A Metric For Token-level Calibration on Large Language Models
by: Liu, Han, et al.
Published: (2024)

ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models
by: Chen, Hao, et al.
Published: (2025)

Revisiting Large Language Model Pruning using Neuron Semantic Attribution
by: Ding, Yizhuo, et al.
Published: (2025)

Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization
by: Wang, Dixuan, et al.
Published: (2024)

Entropy-Based Block Pruning for Efficient Large Language Models
by: Yang, Liangwei, et al.
Published: (2025)

Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification
by: Yun, Jungmin, et al.
Published: (2024)

One Token Is Enough: Improving Diffusion Language Models with a Sink Token
by: Zhang, Zihou, et al.
Published: (2026)

IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining
by: Li, Yixiao, et al.
Published: (2025)

Clickbait Detection via Large Language Models
by: Wang, Han, et al.
Published: (2023)

Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models
by: Wu, Jialiang, et al.
Published: (2025)

Token Constraint Decoding Improves Robustness on Question Answering for Large Language Models
by: Yao, Jui-Ming, et al.
Published: (2025)

Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations
by: Shen, Bowen, et al.
Published: (2024)

EVTP-IVS: Effective Visual Token Pruning For Unifying Instruction Visual Segmentation In Multi-Modal Large Language Models
by: Zhu, Wenhui, et al.
Published: (2025)

Dissecting Failure Dynamics in Large Language Model Reasoning
by: Zhu, Wei, et al.
Published: (2026)

Metacognitive Prompting Improves Understanding in Large Language Models
by: Wang, Yuqing, et al.
Published: (2023)

Target-driven Attack for Large Language Models
by: Zhang, Chong, et al.
Published: (2024)

Large Language Model Pruning
by: Huang, Hanjuan, et al.
Published: (2024)

Enhancing Large Language Models for Mobility Analytics with Semantic Location Tokenization
by: Chen, Yile, et al.
Published: (2025)

VLMQ: Token Saliency-Driven Post-Training Quantization for Vision-language Models
by: Xue, Yufei, et al.
Published: (2025)

Targeted Remasking: Replacing Token Editing with Token-to-Mask Refinement in Discrete Diffusion Language Models
by: Yao, Lin
Published: (2026)

Prompt-based Depth Pruning of Large Language Models
by: Wee, Juyun, et al.
Published: (2025)

Pruning General Large Language Models into Customized Expert Models
by: Zhao, Yirao, et al.
Published: (2025)

When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions
by: Xia, Wei, et al.
Published: (2026)

Token-Efficient Leverage Learning in Large Language Models
by: Zeng, Yuanhao, et al.
Published: (2024)

Dynamic Compressing Prompts for Efficient Inference of Large Language Models
by: Hu, Jinwu, et al.
Published: (2025)

ROSAQ: Rotation-based Saliency-Aware Weight Quantization for Efficiently Compressing Large Language Models
by: Yoon, Junho, et al.
Published: (2025)

Deferred Commitment Decoding for Diffusion Language Models
by: Shu, Yingte, et al.
Published: (2026)

PAT: Pruning-Aware Tuning for Large Language Models
by: Liu, Yijiang, et al.
Published: (2024)

SDMPrune: Self-Distillation MLP Pruning for Efficient Large Language Models
by: Zhu, Hourun, et al.
Published: (2025)